{"success":true,"data":{"author":"Papa, Bhattacharya, Park and Yi (Food AI Nexus)","bucketAccessType":"public","bucketName":"food-ai-nexus/salmonella-serovar-hyperspectral","bucketPrefix":"","category":"Health & Biomedical","cloudProvider":"huggingface","createdAt":"2026-11-19T15:09:27.881Z","description":"Hyperspectral microscopy images of five Salmonella enterica serovars relevant to poultry and foodborne illness (Enteritidis, Infantis, Kentucky, Johannesburg and the monophasic variant 4,[5],12:i:-), released with Papa, Bhattacharya, Park and Yi (2025), Foods 14(15):2737, doi:10.3390/foods14152737. Cultures at 10^5 CFU/mL were imaged with an Olympus BX43 upright microscope, a 100x oil-immersion objective and a HinaLea 4250 hyperspectral camera; 500 hypercubes (100 per serovar) were acquired. images/ holds RGB composites rendered from each hypercube at 620, 550 and 450 nm, one full 1936 x 1216 field of view per PNG, split 70/30 into 350 train and 150 test images balanced by serovar; spectra/ holds single-cell spectral features in Parquet (the same table is published separately as salmonella-serovar-hyperspectral-spectra, 25,972 cells). Supports rapid pathogen identification, hyperspectral image classification and image-spectra fusion. About 0.7 GB; load with datasets.load_dataset. Licensed CC BY 4.0 by the authors; cite the Foods paper.","displayTitle":"Salmonella Serovar Hyperspectral Microscopy: 500 Hypercube Images of Five Serovars for AI Classification","doi":"10.3390/foods14152737","huggingFaceUrl":"https://huggingface.co/datasets/food-ai-nexus/salmonella-serovar-hyperspectral","id":"8abf6e36-996d-537b-ab84-541d175ee308","license":"CC-BY-4.0","licenseEvidenceUrl":"https://huggingface.co/datasets/food-ai-nexus/salmonella-serovar-hyperspectral","objectCountEstimate":504,"probeStatus":"ok","referenceUrl":"https://huggingface.co/datasets/food-ai-nexus/salmonella-serovar-hyperspectral","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"food-ai-nexus/salmonella-serovar-hyperspectral\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"food-ai-nexus/salmonella-serovar-hyperspectral\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=food-ai-nexus, license:cc-by-4.0, size_categories:n<1K, format:imagefolder, downloads=151"],"format":"mixed","generatedAt":"2026-11-19T15:21:55.441Z","layout":{"example":"spectra/test.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"spectra/test.parquet","truncatedAt":512}],"sampleObjects":["images/test/Enteritidis/Enteritidis_evaluate_01.png","images/test/Enteritidis/Enteritidis_evaluate_02.png","images/test/Enteritidis/Enteritidis_evaluate_03.png","images/test/Enteritidis/Enteritidis_evaluate_04.png","images/test/Enteritidis/Enteritidis_evaluate_05.png"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\nlanguage:\n  - en\npretty_name: Salmonella Serovar Hyperspectral Microscopy (Foods 2025)\ntags:\n  - food-safety\n  - salmonella\n  - hyperspectral\n  - microscopy\n  - image-classification\ntask_categories:\n  - image-classification\nconfigs:\n  - config_name: default\n    data_files:\n      - split: train\n        path: images/train/**\n      - split: test\n        path: images/test/**\n---\n\n# Salmonella Serovar Hyperspectral Microscopy (Foods 2025)\n\nSalmonella Serovar Hyperspectral Microscopy is an image dataset for foodborne bacterial classification using hyperspectral imaging. It was created to support research in rapid pathogen identification, enabling models to classify *Salmonella* serovars directly from microscopy images without the need for selective enrichment.\n\n> **Companion spectral dataset:** The single-cell spectral features (tabular, 25,972 rows) extracted from these images are available at [`food-ai-nexus/salmonella-serovar-hyperspectral-spectra`](https://huggingface.co/datasets/food-ai-nexus/salmonella-serovar-hyperspectral-spectra).\n\nThis dataset accompanies the publication: Papa, M., Bhattacharya, S., Park, B., & Yi, J. (2025). Rapid *Salmonella* Serovar Classification Using AI-Enabled Hyperspectral Microscopy with Enhanced Data Preprocessing and Multimodal Fusion. *Foods*, 14(15), 2737. doi: [10.3390/foods14152737](https://doi.org/10.3390/foods14152737)\n\n## Dataset Description\n\nThe dataset contains RGB composite images generated from hyperspectral data cubes (hypercubes) at wavelengths 620 nm (red), 550 nm (green), and 450 nm (blue). Each image represents one full microscopy field of view (1936×1216 pixels).\n\n```python\nfrom datasets import load_dataset\n\nds = load_dataset(\"food-ai-nexus/salmonella-serovar-hyperspectral\")\n# ds['train'] → 350 images | ds['test'] → 150 images\n```\n\n## Splits\n\nThe dataset is split 70/30 into training and testing sets, perfectly balanced across all five serovars.\n\n| Split | Images | Images per Serovar |\n| :--- | ---: | ---: |\n| `train` | 350 | 70 |\n| `test` | 150 | 30 |\n\n## Classes\n\nFive *Salmonella* serovars were selected based on their prevalence in foodborne illness outbreaks and their relevance to poultry safety:\n\n| Class Label | Serovar | Notes |\n| :--- | :--- | :--- |\n| `Enteritidis` | *S.* Enteritidis | Top-5 US foodborne illness serovar |\n| `Infantis` | *S.* Infantis | Linked to antimicrobial-resistant clones |\n| `Kentucky` | *S.* Kentucky | Prevalent in poultry |\n| `Johannesburg` | *S.* Johannesburg | Co-occurs with Enteritidis and Infantis |\n| `I4` | *S.* 4,[5],12:i:- | Monophasic variant; top-5 US foodborne illness serovar |\n\n## Data Collection\n\nBacterial cultures were prepared at 10⁵ CFU/mL in sterile de-ionized water and imaged using an Olympus BX43 upright optical microscope with a 100× oil immersion lens (Olympus UPLFLN 100×) and a HinaLea 4250 hyperspectral camera. A total of 500 hypercubes were acquired (100 per serovar) across six biological replicates (two independent sessions × three subcultures).\n\n## Baseline Performance\n\n| Model | Modality | Test Accuracy |\n| :--- | :--- | ---: |\n| EfficientNetV2 | Image only | 57.3% |\n| PCA-MLP + EfficientNetV2 | Multimodal fusion (Image + Spectra) | **82.4%** |\n\n## License\n\nThis dataset is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) License.\n\n## Citation\n\n```bibtex\n@article{papa2025salmonella,\n  title   = {Rapid Salmonella Serovar Classification Using AI-Enabled Hyperspectral Microscopy with Enhanced Data Preprocessing and Multimodal Fusion},\n  author  = {Papa, MeiLi and Bhattacharya, Siddhartha and Park, Bosoon and Yi, Jiyoon},\n  journal = {Foods},\n  volume  = {14},\n  number  = {15},\n  pages   = {2737},\n  year    = {2025},\n  doi     = {10.3390/foods14152737}\n}\n```\n\n## Source\n\nOriginal dataset: [Zenodo 10.5281/zenodo.16740800](https://zenodo.org/records/16740800)  \nCode repository: [GitHub food-ai-engineering-lab/salmonella-serovar-classification-foods](https://github.com/food-ai-engineering-lab/salmonella-serovar-classification-foods)\n","encoding":"utf8","key":"README.md","name":"README.md","size":4063,"truncated":false}],"sourceObjectKey":"spectra/test.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"food-ai-nexus/salmonella-serovar-hyperspectral\")\nprint(ds)","starterSamplePath":"images/test/Enteritidis/Enteritidis_evaluate_01.png","totalObjects":504},"summary":"Hyperspectral microscopy images of five Salmonella enterica serovars relevant to poultry and foodborne illness (Enteritidis, Infantis, Kentucky, Johannesburg and the monophasic…","title":"Salmonella Serovar Hyperspectral Microscopy: 500 Hypercube Images of Five Serovars for AI Classification","updatedAt":"2026-11-19T19:04:48.316Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/food-ai-nexus/salmonella-serovar-hyperspectral"}}